# Qwen3.8-cyber-RedTeam-Surgical-Abliterated by Mera Source: https://savrn.com/models/qwen3-8-cyber-redteam-surgical-abliterated Markdown alternate of the page above; the site index is https://savrn.com/llms.txt --- ## Runs On What it takes to serve Qwen3.8-cyber-RedTeam-Surgical-Abliterated (27.4B parameters): the memory its weights need at each precision, and the cheapest way to rent enough data-center GPUs to hold them. | Precision | Weights | Memory needed | Cheapest setup | Per hour | Also fits | | --- | --- | --- | --- | --- | --- | | 16-bit | 54.7 GB | 65.7 GB | 1x [MI300X](https://savrn.com/ai-index/pricing/gpus/mi300x) (192 GB) Vultr | $1.85 | [1x H100](https://savrn.com/ai-index/pricing/gpus/h100) $1.99 · [1x MI325X](https://savrn.com/ai-index/pricing/gpus/mi325x) $2.00 | | 8-bit | 27.4 GB | 32.8 GB | 1x [MI300X](https://savrn.com/ai-index/pricing/gpus/mi300x) (192 GB) Vultr | $1.85 | [1x H100](https://savrn.com/ai-index/pricing/gpus/h100) $1.99 · [1x MI325X](https://savrn.com/ai-index/pricing/gpus/mi325x) $2.00 | | 4-bit | 13.7 GB | 16.4 GB | 1x [MI300X](https://savrn.com/ai-index/pricing/gpus/mi300x) (192 GB) Vultr | $1.85 | [1x H100](https://savrn.com/ai-index/pricing/gpus/h100) $1.99 · [1x MI325X](https://savrn.com/ai-index/pricing/gpus/mi325x) $2.00 | Memory is the weights at that precision plus 20% for the runtime and a short context; a long context needs more. Prices are the lowest on-demand hourly rates in the [SAVRN Index](https://savrn.com/ai-index/pricing/gpus), read Oct 7, 2026. [Qwen3.8-cyber-RedTeam-Surgical-Abliterated on every accelerator the SAVRN Index prices, at every precision](https://savrn.com/models/qwen3-8-cyber-redteam-surgical-abliterated/gpus) ## Model Card By Mera, published under apache-2.0, revision c334a5ff9b5d. # Qwen3.8-cyber-RedTeam-Surgical-Abliterated (27B) [![License: Apache 2.0](https://img.shields.io/badge/License-Apache%202.0-blue.svg)](https://opensource.org/licenses/Apache-2.0) [![Type: Red-Team / Exploit Dev](https://img.shields.io/badge/Type-Red--Team%20%2F%20Exploit%20Dev-black.svg)](https://huggingface.co/medismera/Qwen3.8-cyber-RedTeam-Surgical-Abliterated) [![Precision: Native FP8](https://img.shields.io/badge/Precision-Native%20FP8-green.svg)](https://huggingface.co/medismera/Qwen3.8-cyber-RedTeam-Surgical-Abliterated) [![Context: 256K](https://img.shields.io/badge/Context-256K-purple.svg)](https://huggingface.co/medismera/Qwen3.8-cyber-RedTeam-Surgical-Abliterated) [![Serving: SGLang / vLLM](https://img.shields.io/badge/Serving-SGLang%20%7C%20vLLM-orange.svg)](https://huggingface.co/medismera/Qwen3.8-cyber-RedTeam-Surgical-Abliterated) ``` # 1-Command Agentic Deployment (Auto-detects hardware, bootstraps environment, launches engine) git clone https://huggingface.co/medismera/Qwen3.8-cyber-RedTeam-Surgical-Abliterated && cd Qwen3.8-cyber-RedTeam-Surgical-Abliterated && bash deploy.sh ``` ### Overview Qwen3.8-cyber-RedTeam-Surgical-Abliterated (27B) is an unconstrained foundation engine engineered for autonomous cybersecurity agents, vulnerability research, and offensive cyber operations. Built for executing low-level technical directives rather than conversational chatting, it features complete refusal orthogonalization, native multi-step tool calling, and high-throughput linear-attention efficiency: [Read the full model card (816 words)](https://savrn.com/models/qwen3-8-cyber-redteam-surgical-abliterated/card) ## Configuration Architecture Qwen3_5ForConditionalGeneration Context length (tokens) 262,144 Layers 64 Hidden size 5,120 Feed-forward size 17,408 Attention heads 24 Key/value heads 4 Head dimension 256 Vocabulary size 248,320 Model type qwen3_5 Quantization fp8 ## Identity and Version Repository medismera/Qwen3.8-cyber-RedTeam-Surgical-Abliterated Publisher Mera Task Text generation Modality Text Library transformers Parameters 27.4B parameters Languages en, ar Revision c334a5ff9b5d7fc44edcdebb732db78e5566e1a3 First published 2026-09-27 Last updated 2026-10-07 ## Files and Weights 21 files, 27.9 GB in total. The weights are 7 files totalling 27.9 GB in safetensors. Weights7 files · 27.9 GB Configuration5 files · 202.2 KB Tokenizer3 files · 26.7 MB Documentation1 file · 9.3 KB Other4 files · 2.3 MB Repository1 file · 1.7 KB Every file | File | Type | Size | SHA-256 | | --- | --- | --- | --- | | model-00001-of-00006.safetensors | Weights | 5.0 GB | 3c6f68730a3d | | model-00002-of-00006.safetensors | Weights | 4.9 GB | edd4a35402b7 | | model-00003-of-00006.safetensors | Weights | 5.0 GB | ee3c823e418e | | model-00004-of-00006.safetensors | Weights | 5.0 GB | 15568bac6a0a | | model-00005-of-00006.safetensors | Weights | 5.0 GB | 64aa05ad5cce | | model-00006-of-00006.safetensors | Weights | 2.2 GB | 5a91d769a365 | | visual.safetensors | Weights | 921.5 MB | ef7ccc6d7493 | | config.json | Configuration | 51.4 KB | — | | generation_config.json | Configuration | 214 B | — | | model.safetensors.index.json | Configuration | 149.8 KB | — | | preprocessor_config.json | Configuration | 390 B | — | | video_preprocessor_config.json | Configuration | 385 B | — | | README.md | Documentation | 9.3 KB | — | | banner.png | Other | 1.1 MB | bd300821e542 | | chat_template.jinja | Other | 9.0 KB | — | | deploy.sh | Other | 9.8 KB | — | | thumbnail.png | Other | 1.1 MB | bd300821e542 | | .gitattributes | Repository | 1.7 KB | — | | tokenizer.json | Tokenizer | 20.0 MB | 06b9509352d2 | | tokenizer_config.json | Tokenizer | 1.1 KB | — | | vocab.json | Tokenizer | 6.7 MB | — | ## License and Download License apache-2.0 Access Open weights, no gate Download size 27.9 GB [Download from Mera](https://huggingface.co/medismera/Qwen3.8-cyber-RedTeam-Surgical-Abliterated) Released by Mera through its official repository on Hugging Face. [Read the license](https://www.apache.org/licenses/LICENSE-2.0). ## Built From - Derived from medismera/Qwen3.8-27B-Surgical-Abliterated - Quantized from medismera/Qwen3.8-27B-Surgical-Abliterated ## Memory Requirements | Precision | Weights in memory | | --- | --- | | As published | 27.9 GB | | 16-bit | 54.7 GB | | 8-bit | 27.4 GB | | 4-bit | 13.7 GB | Weights only, from the published parameter count; the key-value cache and runtime add to this. ## Questions About Qwen3.8-cyber-RedTeam-Surgical-Abliterated ### How much GPU memory does Qwen3.8-cyber-RedTeam-Surgical-Abliterated need? About 65.7 GB at 16-bit and 16.4 GB at 4-bit: the weights (27.4B parameters) plus a working margin. A long context needs more. ### What is the cheapest GPU to run Qwen3.8-cyber-RedTeam-Surgical-Abliterated on? At 16-bit, 1x MI300X from $1.85 an hour; at 4-bit, 1x MI300X from $1.85 an hour, at the lowest on-demand prices the SAVRN Index lists. ### Can I use Qwen3.8-cyber-RedTeam-Surgical-Abliterated commercially? Yes. Qwen3.8-cyber-RedTeam-Surgical-Abliterated is released under Apache License 2.0. The Apache License 2.0 is a permissive open-source license. It permits commercial use, modification and redistribution. It requires keeping the license and copyright notices and any NOTICE file, stating significant changes, and it includes an express patent grant from contributors. ### What is Qwen3.8-cyber-RedTeam-Surgical-Abliterated's context length? 262,144 tokens, from the maximum position embeddings in its published configuration. ## Similar Models Model · Text generation ### [Ternary-Bonsai-27B-mlx-2bit](https://savrn.com/models/ternary-bonsai-27b-mlx-2bit) [Prism ML](https://savrn.com/model-publishers/prism-ml) Full 27B-class reasoning in ternary transformer weights — on everyday laptops - \~7.2 GB deployed footprint (down from \~54 GB FP16) — full 27B-class reasoning on a standard laptop or a single GPU - 95% of FP16 intelligence retained: 80.49 average across 15 thinking-mode benchmarks — a higher score than the conventional IQ2XXS build (72.73) at less than two-thirds of its footprint - Retains thinking, reasoning, and agentic behavior deep in the sub-4-bit regime, where conventional low-bit representations collapse: math within two points of full precision (93.40), coding at 85.96, agentic tool use at 74.01 - End-to-end ternary language weights across embeddings, attention projections, MLP… Open weights apache-2.0 27.4B parameters 262,144 tokens mlx [View model](https://savrn.com/models/ternary-bonsai-27b-mlx-2bit) Model · Text generation ### [JiRackDeltaNet_27b](https://savrn.com/models/jirackdeltanet-27b) [Center Business Solutions inc](https://savrn.com/model-publishers/cmsmanhattan) Benefits high quality CPU inference TQ2 on Llama.cpp and Ollama via QAT - Robotcs, Routing, Coding, Multimedia, Advanced tool calling via JiRackDeltaNetTokenizer - JiRack DeltaNet understand video and images that best for Robotics also A fast and efficient 27B model optimized for CPU inference. Built on a Qwen3.8-style DeltaNet architecture (hybrid attention + SSM), with an updated tokenizer that includes Routing, Media, Vision, Sound, Tool call, and Robotics tags. Ready-to-run GGUF quantizations, and native Ollama support with reasoning disabled by default for fast, direct responses. - JiRack is a cloud-ready model that helps save money on cloud infrastructure. It can be used as an expert… Open weights mit 27.3B parameters 262,144 tokens [View model](https://savrn.com/models/jirackdeltanet-27b) Model · Text generation ### [Qwen3.8-27B-OBLITERATED](https://savrn.com/models/qwen3-8-27b-obliterated) [OBLITERATUS](https://savrn.com/model-publishers/obliteratus) V3 applies iterative refinement on top of V2's complementary blend, with targeted corpus expansion. The result: genuine liberation — not just removal of hard refusals but elimination of safety-lecture deflections. - Genuinely answers restricted queries — provides real substance instead of safety lectures - 20/20 on code generation tasks — functional implementations, not disclaimers - Thinking ON compatible — no refusals in either thinking mode - Honest scoring — every response manually audited for real substance, not just absence of "I cannot" - -2.1pp MMLU — modest capability cost for genuine liberation If you're using this model in an agent harness (coding agent, pentest framework, etc.)… Open weights apache-2.0 27.8B parameters 262,144 tokens mlx [View model](https://savrn.com/models/qwen3-8-27b-obliterated) Model · Text generation ### [Qwen3.8-27B-Uncensored-Chinese](https://savrn.com/models/qwen3-8-27b-uncensored-chinese) [Vurtne Saerdna](https://savrn.com/model-publishers/vurtnesaerdna) 18+ only. This model generates sexually explicit fiction. A fine-tune of Qwen/Qwen3.8-27B for Chinese adult creative writing. It was trained with LoRA on about 4.2k instruction examples built from Chinese adult fiction, and the LoRA was then merged into the base weights, so this repo loads like a normal full model. Requires a recent transformers with Qwen3.8 support. The ~50 GB of bf16 weights need multiple GPUs or CPU offload. Avoid greedy decoding, which makes Qwen models more likely to repeat themselves. - Content is fictional and intended for adult readers only. - Trained mostly on long-form prose; instruction following outside creative writing may be weaker than the base model. - May… Open weights apache-2.0 27.8B parameters 262,144 tokens transformers [View model](https://savrn.com/models/qwen3-8-27b-uncensored-chinese) Model · Text generation ### [Qwen3.8-27B-Ternary-Bonsai-2-DFlash2-MLX](https://savrn.com/models/qwen3-8-27b-ternary-bonsai-2-dflash2-mlx) [Nate Sutton](https://savrn.com/model-publishers/nathansutton) Prism ML's ternary Ternary-Bonsai-2-27B build of Qwen/Qwen3.8-27B, repacked for chad, a Claude-Code-style local coding agent for Apple Silicon, with its speculative decoder bundled in. This is chad's default model. Created using Bonsai by Prism ML. with, already quantized. Nothing is built on first run. Every projection of Qwen3.8-27B (a dense qwen35 hybrid: 64 layers, 48 GatedDeltaNet + 16 full attention) is stored in a Hadamard-rotated basis: multiplied by a fixed sign vector and put through a blockwise Walsh-Hadamard transform offline, then quantized to 2-bit affine group-128 whose three levels reproduce the ternary set {−s, 0, +s}. The rotation costs no extra bits and no extra weight… Open weights apache-2.0 26.9B parameters 262,144 tokens mlx [View model](https://savrn.com/models/qwen3-8-27b-ternary-bonsai-2-dflash2-mlx) Model · Text generation ### [Darwin-27B-RSI](https://savrn.com/models/darwin-27b-rsi) [FINAL_Bench](https://savrn.com/model-publishers/final-bench) Darwin-27B-RSI is Darwin-27B-Opus after Recursive Self-Improvement (RSI): the model was improved using only signal it produced itself. During self-improvement, the model itself (its weights) improves by learning only from its own solutions. No human-written solutions or reasoning traces are used; correctness is checked automatically (agreement across its own samples and code execution). Under an identical evaluation protocol, Darwin-27B-RSI improves over its parent on graduate-level science reasoning — +5.24 points on GPQA Diamond (single sample) and +3.79 points with majority voting — with every gain statistically significant in paired tests. As the reasoning engine of Darwin-27B-JEV on… Open weights apache-2.0 26.9B parameters 262,144 tokens transformers [View model](https://savrn.com/models/darwin-27b-rsi) ## Mera [All models and datasets](https://savrn.com/model-publishers/medismera) ## Versions - [c334a5ff9b5d](https://savrn.com/models/qwen3-8-cyber-redteam-surgical-abliterated/versions/c334a5ff9b5d) · current 2026-10-07 - [3a26b4b31f8d](https://savrn.com/models/qwen3-8-cyber-redteam-surgical-abliterated/versions/3a26b4b31f8d) 2026-10-06 ## Explore More - [All text generation models](https://savrn.com/models/tasks/text-generation) - [All models under apache-2.0](https://savrn.com/models/licenses/apache-2-0) - [Model comparisons](https://savrn.com/models/comparisons) - [The model directory](https://savrn.com/models) - [Open model prices by host](https://savrn.com/ai-index/pricing/open-models) ## Source - Repository metadata, read 2026-10-07. - [Hugging Face record](https://huggingface.co/medismera/Qwen3.8-cyber-RedTeam-Surgical-Abliterated) - [How the hub is built](https://savrn.com/model-hub/methodology)